faster resize?

Makefile

@@ -1,5 +1,5 @@
-GPU=0
-OPENCV=0
+GPU=1
+OPENCV=1
 DEBUG=0
 
 ARCH= -arch=sm_52

cfg/yolo.cfg

@@ -1,6 +1,6 @@
 [net]
 batch=64
-subdivisions=64
+subdivisions=2
 height=448
 width=448
 channels=3

src/data.c

@@ -425,10 +425,18 @@ data load_data_detection_jitter_random(int n, char **paths, int m, int classes,
     d.X.vals = calloc(d.X.rows, sizeof(float*));
     d.X.cols = h*w*3;
 
+    clock_t time;
+    clock_t load = 0;
+    clock_t resize = 0;
+    clock_t crop = 0;
+
     int k = num_boxes*num_boxes*(4+classes+background);
     d.y = make_matrix(n, k);
     for(i = 0; i < n; ++i){
+        time=clock();
         image orig = load_image_color(random_paths[i], 0, 0);
+        load += clock() - time;
+        time = clock();
 
         int oh = orig.h;
         int ow = orig.w;
@@ -456,17 +464,26 @@ data load_data_detection_jitter_random(int n, char **paths, int m, int classes,
 
         int flip = rand_r(&data_seed)%2;
         image cropped = crop_image(orig, pleft, ptop, swidth, sheight);
+
+        crop += clock() - time;
+        time = clock();
+
         float dx = ((float)pleft/ow)/sx;
         float dy = ((float)ptop /oh)/sy;
 
-        free_image(orig);
         image sized = resize_image(cropped, w, h);
-        free_image(cropped);
         if(flip) flip_image(sized);
         d.X.vals[i] = sized.data;
 
+        resize += clock() - time;
+        time = clock();
+
         fill_truth_detection(random_paths[i], d.y.vals[i], classes, num_boxes, flip, background, dx, dy, 1./sx, 1./sy);
+
+        free_image(orig);
+        free_image(cropped);
     }
+    printf("load: %f, crop: %f, resize: %f\n", sec(load), sec(crop), sec(resize));
     free(random_paths);
     return d;
 }

src/image.c

@@ -584,6 +584,51 @@ image resize_image(image im, int w, int h)
     return resized;
 }
 
+image resize_image2(image im, int w, int h)
+{
+    image resized = make_image(w, h, im.c);   
+    image part = make_image(w, im.h, im.c);
+    int r, c, k;
+    float w_scale = (float)(im.w - 1) / (w - 1);
+    float h_scale = (float)(im.h - 1) / (h - 1);
+    for(k = 0; k < im.c; ++k){
+        for(r = 0; r < im.h; ++r){
+            for(c = 0; c < w; ++c){
+                float val = 0;
+                if(c == w-1){
+                    val = get_pixel(im, im.w-1, r, k);
+                } else {
+                    float sx = c*w_scale;
+                    int ix = (int) sx;
+                    float dx = sx - ix;
+                    val = (1 - dx) * get_pixel(im, ix, r, k) + dx * get_pixel(im, ix+1, r, k);
+                }
+                set_pixel(part, c, r, k, val);
+            }
+        }
+    }
+
+    for(k = 0; k < im.c; ++k){
+        for(r = 0; r < h; ++r){
+            float sy = r*h_scale;
+            int iy = (int) sy;
+            float dy = sy - iy;
+            for(c = 0; c < w; ++c){
+                float val = (1-dy) * get_pixel(part, c, iy, k);
+                set_pixel(resized, c, r, k, val);
+            }
+            if(r == h-1) continue;
+            for(c = 0; c < w; ++c){
+                float val = dy * get_pixel(part, c, iy+1, k);
+                add_pixel(resized, c, r, k, val);
+            }
+        }
+    }
+
+    free_image(part);
+    return resized;
+}
+
 void test_resize(char *filename)
 {
     image im = load_image(filename, 0,0, 3);
@@ -728,6 +773,11 @@ void set_pixel(image m, int x, int y, int c, float val)
     assert(x < m.w && y < m.h && c < m.c);
     m.data[c*m.h*m.w + y*m.w + x] = val;
 }
+void add_pixel(image m, int x, int y, int c, float val)
+{
+    assert(x < m.w && y < m.h && c < m.c);
+    m.data[c*m.h*m.w + y*m.w + x] += val;
+}
 
 void print_image(image m)
 {

src/image.h

@@ -28,6 +28,7 @@ image image_distance(image a, image b);
 void scale_image(image m, float s);
 image crop_image(image im, int dx, int dy, int w, int h);
 image resize_image(image im, int w, int h);
+image resize_image2(image im, int w, int h);
 void translate_image(image m, float s);
 void normalize_image(image p);
 image rotate_image(image m, float rad);
@@ -62,6 +63,7 @@ image load_image_color(char *filename, int w, int h);
 float get_pixel(image m, int x, int y, int c);
 float get_pixel_extend(image m, int x, int y, int c);
 void set_pixel(image m, int x, int y, int c, float val);
+void add_pixel(image m, int x, int y, int c, float val);
 float billinear_interpolate(image im, float x, float y, int c);
 
 image get_image_layer(image m, int l);